AI Blog

AI Blog

by Michele Laurelli

GAN (Generative Adversarial Network)

/ɡæn/
Architecture
Definition

A framework where two neural networks compete: a generator creates fake data and a discriminator tries to distinguish real from fake.

GANs consist of a generator and discriminator trained adversarially. The generator improves at creating realistic data while the discriminator improves at detection. Used for image generation, style transfer, and data augmentation.

Examples

1

StyleGAN for face generation

2

CycleGAN for image-to-image translation

3

Pix2Pix for paired image translation

Michele Laurelli - AI Research & Engineering